Gesture-Integrated Speech Recognition for False Trigger Reduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current speech recognition systems are limited by false triggering during normal conversation and require users to learn complex interfaces, making them cumbersome and inefficient, especially in hands-free applications.

Innovation Solution

The system performs speech recognition using sensory inputs of human position, such as changes in orientation, direction, or gestures, by selecting a recognition set based on detected body movements and integrating this information with speech input signals to improve accuracy and user interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If speech recognition is used alone, then hands-free operation is enabled, but false triggering occurs during normal conversation

Engineering Contradiction:

Improvehands-free operationVSAvoidfalse triggering

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent combines speech recognition with gesture recognition to create a hybrid input system. The gesture detector captures hand movements while the speech recognizer processes verbal commands, and both inputs are integrated to control the electronic device, reducing false triggering while maintaining hands-free operation

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The gesture detection system serves as an intermediary mechanism that validates speech commands. By requiring both gesture and speech inputs to match the desired command, the system acts as a mediator that filters out false speech triggers during normal conversation

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If traditional button interfaces are used, then device functions are accessible, but user learning time increases

Engineering Contradiction:

Improveinterface accessibilityVSAvoiduser learning time

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The gesture recognition system allows users to interact with the device using natural hand movements that intuitively correspond to desired actions. Users can point at objects or perform gestures that naturally map to device functions, eliminating the need to learn complex button sequences or menu structures

Inventive Principle:

Principle #25Self-service

3Adaptability or versatility

If speech recognition vocabulary is expanded, then more commands are recognized, but false triggering increases

Engineering Contradiction:

Improvecommand recognition rangeVSAvoidfalse triggering

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system merges speech recognition with gesture recognition to create a dual-input verification mechanism. Even with an expanded vocabulary, both speech and gesture must align with the intended command, preventing false triggering while maintaining broad command recognition capabilities

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS8321219B2Systems and methods of performing speech recognition using gestures

Publication Date: 2012.11.27 SENSORY INC

AI summary

Embodiments of the present invention improve methods of performing speech recognition using human gestures. In one embodiment, the present invention includes a speech recognition method comprising detecting a gesture, selecting a first recognition set based on the gesture, receiving a speech input signal, and recognizing the speech input signal in the context of the first recognition set.